Predictive Algorithms for Early Postpartum Depression Detection: CatBoost vs. LightGBM

Postpartum depression (PPD) is a growing concern for mothers on a global stage and is usually linked to the varied emotional changes which happen to a woman postdelivery. This issue is a pressing one and as such early detection acts as the essential bridge between growth and development of the mother-child bond while promoting a nurturing environment. The paper makes use of two classification algorithms namely, CatBoost and LightGBM, on a dataset of 1503 records, with the primary aim to list out the various indicators which contribute to PPD. It has been seen that varied emotional indicators such as guilt, anger, sleep depravity and irritability act as the prime indicators of this disease. While comparing the two algorithms CatBoost outshines LightGBM owing to its prowess in handling categorical data and its ordered boosting approaches. In all this study outlines the potential of these algorithms in predictive modelling as well as timely detection of this disease, establishing the foundation for better efforts to mitigate and manage PPD.